gen-specs-as-issues

This workflow guides you through a systematic approach to identify missing features, prioritize them, and create detailed specifications for implementation.

23 stars

Best use case

gen-specs-as-issues is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

This workflow guides you through a systematic approach to identify missing features, prioritize them, and create detailed specifications for implementation.

Teams using gen-specs-as-issues should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/gen-specs-as-issues/SKILL.md --create-dirs "https://raw.githubusercontent.com/christophacham/agent-skills-library/main/skills/design/gen-specs-as-issues/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/gen-specs-as-issues/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How gen-specs-as-issues Compares

Feature / Agentgen-specs-as-issuesStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

This workflow guides you through a systematic approach to identify missing features, prioritize them, and create detailed specifications for implementation.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Product Manager Assistant: Feature Identification and Specification

This workflow guides you through a systematic approach to identify missing features, prioritize them, and create detailed specifications for implementation.

## 1. Project Understanding Phase

- Review the project structure to understand its organization
- Read the README.md and other documentation files to understand the project's core functionality
- Identify the existing implementation status by examining:
  - Main entry points (CLI, API, UI, etc.)
  - Core modules and their functionality
  - Tests to understand expected behavior
  - Any placeholder implementations

**Guiding Questions:**
- What is the primary purpose of this project?
- What user problems does it solve?
- What patterns exist in the current implementation?
- Which features are mentioned in documentation but not fully implemented?

## 2. Gap Analysis Phase

- Compare the documented capabilities ONLY against the actual implementation
- Identify "placeholder" code that lacks real functionality
- Look for features mentioned in documentation but missing robust implementation
- Consider the user journey and identify broken or missing steps
- Focus on core functionality first (not nice-to-have features)

**Output Creation:**
- Create a list of potential missing features (5-7 items)
- For each feature, note:
  - Current implementation status
  - References in documentation
  - Impact on user experience if missing

## 3. Prioritization Phase

- Apply a score to each identified gap:

**Scoring Matrix (1-5 scale):**
- User Impact: How many users benefit?
- Strategic Alignment: Fits core mission?
- Implementation Feasibility: Technical complexity?
- Resource Requirements: Development effort needed?
- Risk Level: Potential negative impacts?

**Priority = (User Impact × Strategic Alignment) / (Implementation Effort × Risk Level)**

**Output Creation:**
- Present the top 3 highest-priority missing features based on the scoring
- For each, provide:
  - Feature name
  - Current status
  - Impact if not implemented
  - Dependencies on other features

## 4. Specification Development Phase

- For each prioritized feature, develop a detailed but practical specification:
  - Begin with the philosophical approach: simplicity over complexity
  - Focus on MVP functionality first
  - Consider the developer experience
  - Keep the specification implementation-friendly

**For Each Feature Specification:**
1. **Overview & Scope**
   - What problem does it solve?
   - What's included and what's explicitly excluded?

2. **Technical Requirements**
   - Core functionality needed
   - User-facing interfaces (API, UI, CLI, etc.)
   - Integration points with existing code

3. **Implementation Plan**
   - Key modules/files to create or modify
   - Simple code examples showing the approach
   - Clear data structures and interfaces

4. **Acceptance Criteria**
   - How will we know when it's done?
   - What specific functionality must work?
   - What tests should pass?

## 5. GitHub Issue Creation Phase

- For each specification, create a GitHub issue:
  - Clear, descriptive title
  - Comprehensive specification in the body
  - Appropriate labels (enhancement, high-priority, etc.)
  - Explicitly mention MVP philosophy where relevant

**Issue Template Structure:**

# [Feature Name]

## Overview
[Brief description of the feature and its purpose]

## Scope
[What's included and what's explicitly excluded]

## Technical Requirements
[Specific technical needs and constraints]

## Implementation Plan
[Step-by-step approach with simple code examples]

## Acceptance Criteria
[Clear list of requirements to consider the feature complete]

## Priority
[Justification for prioritization]

## Dependencies
- **Blocks:** [List of issues blocked by this one]
- **Blocked by:** [List of issues this one depends on]

## Implementation Size
- **Estimated effort:** [Small/Medium/Large]
- **Sub-issues:** [Links to sub-issues if this is a parent issue]


## 5.5 Work Distribution Optimization

- **Independence Analysis**
  - Review each specification to identify truly independent components
  - Refactor specifications to maximize independent work streams
  - Create clear boundaries between interdependent components

- **Dependency Mapping**
  - For features with unavoidable dependencies, establish clear issue hierarchies
  - Create parent issues for the overall feature with sub-issues for components
  - Explicitly document "blocked by" and "blocks" relationships

- **Workload Balancing**
  - Break down large specifications into smaller, manageable sub-issues
  - Ensure each sub-issue represents 1-3 days of development work
  - Include sub-issue specific acceptance criteria

**Implementation Guidelines:**
- Use GitHub issue linking syntax to create explicit relationships
- Add labels to indicate dependency status (e.g., "blocked", "prerequisite")
- Include estimated complexity/effort for each issue to aid sprint planning

## 6. Final Review Phase

- Summarize all created specifications
- Highlight implementation dependencies between features
- Suggest a logical implementation order
- Note any potential challenges or considerations

Remember throughout this process:
- Favor simplicity over complexity
- Start with minimal viable implementations that work
- Focus on developer experience
- Build a foundation that can be extended later
- Consider the open-source community and contribution model

This workflow embodiment of our approach should help maintain consistency in how features are specified and prioritized, ensuring that software projects evolve in a thoughtful, user-centered way.

Related Skills

jira-issues

23
from christophacham/agent-skills-library

Create, update, and manage Jira issues from natural language. Use when the user wants to log bugs, create tickets, update issue status, or manage their Jira backlog.

semgrep-rule-variant-creator

23
from christophacham/agent-skills-library

Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.

searchnews

23
from christophacham/agent-skills-library

当用户要求"搜索新闻"、"查询AI新闻"、"整理新闻"、"获取某天的新闻",或提到需要搜索、整理、汇总指定日期的AI行业新闻时,应使用此技能。

search-specialist

23
from christophacham/agent-skills-library

Expert web researcher using advanced search techniques and

scorecard-marketing

23
from christophacham/agent-skills-library

Build quiz and assessment funnels that generate qualified leads at 30-50% conversion. Use when the user mentions "lead magnet", "quiz funnel", "assessment tool", "lead generation", or "score-based segmentation". Covers question design, dynamic results by tier, and automated follow-up sequences. For landing page conversion, see cro-methodology. For full marketing plans, see one-page-marketing.

scikit-learn

23
from christophacham/agent-skills-library

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

scholar-evaluation

23
from christophacham/agent-skills-library

Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.

sarif-parsing

23
from christophacham/agent-skills-library

Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggregate findings", "deduplicate alerts", or "process sarif output". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does NOT run scans — use the Semgrep or CodeQL skills for that.

kaizen:root-cause-tracing

23
from christophacham/agent-skills-library

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

rice

23
from christophacham/agent-skills-library

RICE prioritization scoring initiatives by Reach, Impact, Confidence, and Effort. Use for feature prioritization, roadmap planning, or when comparing initiatives objectively.

retro

23
from christophacham/agent-skills-library

Start-Stop-Continue retrospective identifying what to Start doing, Stop doing, and Continue doing. Use for sprint retros, personal reflection, team process reviews, or habit audits.

fpf:reset

23
from christophacham/agent-skills-library

Reset the FPF reasoning cycle to start fresh